© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48367
    Prev
    Next
    INDEX
    Explanations

    `from` and `require` followed by paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .php
    -0.08
    åĿIJéªij
    -0.08
    woff
    -0.08
    ä¸įåı¯åıĬ
    -0.07
    иÑĢ
    -0.07
    ison
    -0.07
    .twig
    -0.07
     اÙĦÙĪ
    -0.07
    ÏĢί
    -0.07
    /twitter
    -0.07
    POSITIVE LOGITS
    åĬłæĭ¿å¤§
    0.08
    ouro
    0.08
    ìļ´ëį°
    0.07
    奶çĪ¸
    0.07
    _;
    0.07
    odi
    0.07
    _native
    0.06
    åıĤèĢĥ
    0.06
    olé
    0.06
    anke
    0.06
    Activations Density 0.029%

    No Known Activations